© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16044
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ométrie
    -0.48
     IBOutlet
    -0.47
    def
    -0.47
    ljeno
    -0.47
    ‿
    -0.46
    _->
    -0.45
     lateinit
    -0.45
    mens
    -0.45
    rdom
    -0.45
    بوابة
    -0.44
    POSITIVE LOGITS
     Wikimedijinoj
    0.74
    tagHelperRunner
    0.68
    OGND
    0.65
    adaptiveStyles
    0.61
    LookAnd
    0.60
     NSCoder
    0.58
    PerformLayout
    0.57
    FunctionFlags
    0.56
    ThroughAttribute
    0.56
     Streak
    0.54
    Activations Density 0.024%

    No Known Activations